路由查询引擎与子问题查询引擎¶

本笔记本将演示以下内容：

1. 路由查询引擎 - 处理用户查询以从预定义索引中进行选择。
2. 子问题查询引擎 - 将复杂查询分解为针对每个相关数据源的子问题，然后收集所有中间响应并综合成最终答案。

路由查询引擎文档

子问题查询引擎文档

路由查询引擎¶

路由器是专门处理用户查询的模块，能够从一组预定义的选项中进行选择，每个选项都由特定元数据定义。

核心路由模块主要有两种类型：

1. LLM 选择器：这类模块将可用选项以文本提示形式呈现，并利用 LLM 文本补全端点进行决策。

2. Pydantic 选择器：这类模块将选项格式化为 Pydantic 模式，传递给函数调用端点，并以 Pydantic 对象形式返回结果。

安装¶

In [ ]:

!pip install llama-index

!pip install llama-index

In [ ]:

# NOTE: This is ONLY necessary in jupyter notebook.
# Details: Jupyter runs an event-loop behind the scenes.
#          This results in nested event-loops when we start an event-loop to make async queries.
#          This is normally not allowed, we use nest_asyncio to allow it for convenience.
import nest_asyncio

nest_asyncio.apply()

# NOTE: This is ONLY necessary in jupyter notebook. # Details: Jupyter runs an event-loop behind the scenes. # This results in nested event-loops when we start an event-loop to make async queries. # This is normally not allowed, we use nest_asyncio to allow it for convenience. import nest_asyncio nest_asyncio.apply()

In [ ]:

import logging
import sys

# Set up the root logger
logger = logging.getLogger()
logger.setLevel(logging.INFO)  # Set logger level to INFO

# Clear out any existing handlers
logger.handlers = []

# Set up the StreamHandler to output to sys.stdout (Colab's output)
handler = logging.StreamHandler(sys.stdout)
handler.setLevel(logging.INFO)  # Set handler level to INFO

# Add the handler to the logger
logger.addHandler(handler)

from llama_index.core import (
    VectorStoreIndex,
    SummaryIndex,
    SimpleDirectoryReader,
    ServiceContext,
    StorageContext,
)

import openai
import os
from IPython.display import display, HTML


# Setup openai api key
os.environ["OPENAI_API_KEY"] = "sk-..."

import logging import sys # Set up the root logger logger = logging.getLogger() logger.setLevel(logging.INFO) # Set logger level to INFO # Clear out any existing handlers logger.handlers = [] # Set up the StreamHandler to output to sys.stdout (Colab's output) handler = logging.StreamHandler(sys.stdout) handler.setLevel(logging.INFO) # Set handler level to INFO # Add the handler to the logger logger.addHandler(handler) from llama_index.core import ( VectorStoreIndex, SummaryIndex, SimpleDirectoryReader, ServiceContext, StorageContext, ) import openai import os from IPython.display import display, HTML # Setup openai api key os.environ["OPENAI_API_KEY"] = "sk-..."

NumExpr defaulting to 2 threads.

下载数据¶

In [ ]:

!mkdir -p 'data/paul_graham/'
!wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/docs/examples/data/paul_graham/paul_graham_essay.txt' -O 'data/paul_graham/paul_graham_essay.txt'

!mkdir -p 'data/paul_graham/' !wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/docs/examples/data/paul_graham/paul_graham_essay.txt' -O 'data/paul_graham/paul_graham_essay.txt'

--2024-05-16 05:27:42--  https://raw.githubusercontent.com/run-llama/llama_index/main/docs/docs/examples/data/paul_graham/paul_graham_essay.txt
Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.108.133, 185.199.110.133, 185.199.111.133, ...
Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.108.133|:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: 75042 (73K) [text/plain]
Saving to: ‘data/paul_graham/paul_graham_essay.txt’


          data/paul   0%[                    ]       0  --.-KB/s               
data/paul_graham/pa 100%[===================>]  73.28K  --.-KB/s    in 0.002s  

2024-05-16 05:27:42 (46.3 MB/s) - ‘data/paul_graham/paul_graham_essay.txt’ saved [75042/75042]

加载数据¶

In [ ]:

# load documents
documents = SimpleDirectoryReader("data/paul_graham").load_data()

# load documents documents = SimpleDirectoryReader("data/paul_graham").load_data()

创建节点¶

In [ ]:

from llama_index.core.text_splitter import SentenceSplitter

# create parser and parse document into nodes
parser = SentenceSplitter(chunk_size=1024, chunk_overlap=100)
nodes = parser(documents)

from llama_index.core.text_splitter import SentenceSplitter # create parser and parse document into nodes parser = SentenceSplitter(chunk_size=1024, chunk_overlap=100) nodes = parser(documents)

创建 VectorStoreIndex 和 SummaryIndex¶

In [ ]:

# Summary Index for summarization questions
summary_index = SummaryIndex(nodes)

# Vector Index for answering specific context questions
vector_index = VectorStoreIndex(nodes)

# Summary Index for summarization questions summary_index = SummaryIndex(nodes) # Vector Index for answering specific context questions vector_index = VectorStoreIndex(nodes)

HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK"

定义查询引擎¶

1. 摘要索引查询引擎
2. 向量索引查询引擎

In [ ]:

# Summary Index Query Engine
summary_query_engine = summary_index.as_query_engine(
    response_mode="tree_summarize",
    use_async=True,
)

# Vector Index Query Engine
vector_query_engine = vector_index.as_query_engine()

# Summary Index Query Engine summary_query_engine = summary_index.as_query_engine( response_mode="tree_summarize", use_async=True, ) # Vector Index Query Engine vector_query_engine = vector_index.as_query_engine()

构建摘要索引与向量索引工具¶

In [ ]:

from llama_index.core.tools.query_engine import QueryEngineTool, ToolMetadata

# Summary Index tool
summary_tool = QueryEngineTool.from_defaults(
    query_engine=summary_query_engine,
    description="Useful for summarization questions related to Paul Graham eassy on What I Worked On.",
)

# Vector Index tool
vector_tool = QueryEngineTool.from_defaults(
    query_engine=vector_query_engine,
    description="Useful for retrieving specific context from Paul Graham essay on What I Worked On.",
)

from llama_index.core.tools.query_engine import QueryEngineTool, ToolMetadata # Summary Index tool summary_tool = QueryEngineTool.from_defaults( query_engine=summary_query_engine, description="Useful for summarization questions related to Paul Graham eassy on What I Worked On.", ) # Vector Index tool vector_tool = QueryEngineTool.from_defaults( query_engine=vector_query_engine, description="Useful for retrieving specific context from Paul Graham essay on What I Worked On.", )

定义路由查询引擎¶

您可以使用多种选择器，每种选择器都具有独特特性。

Pydantic 选择器（仅由 gpt-4 和默认的 gpt-3.5-turbo 支持）利用 OpenAI 函数调用 API。它们不解析原始 JSON，而是生成 pydantic 选择对象。

另一方面，LLM 选择器使用 LLM 生成 JSON 输出，随后解析该输出来查询相关索引。

对于这两种选择器类型，您可以选择路由到单个索引或多个索引。

PydanticSingleSelector¶

利用 OpenAI 函数 API 在底层为路由选择器生成/解析 pydantic 对象。

In [ ]:

from llama_index.core.query_engine.router_query_engine import RouterQueryEngine
from llama_index.core.selectors.llm_selectors import (
    LLMSingleSelector,
    LLMMultiSelector,
)
from llama_index.core.selectors.pydantic_selectors import (
    PydanticMultiSelector,
    PydanticSingleSelector,
)

# Create Router Query Engine
query_engine = RouterQueryEngine(
    selector=PydanticSingleSelector.from_defaults(),
    query_engine_tools=[
        summary_tool,
        vector_tool,
    ],
)

from llama_index.core.query_engine.router_query_engine import RouterQueryEngine from llama_index.core.selectors.llm_selectors import ( LLMSingleSelector, LLMMultiSelector, ) from llama_index.core.selectors.pydantic_selectors import ( PydanticMultiSelector, PydanticSingleSelector, ) # Create Router Query Engine query_engine = RouterQueryEngine( selector=PydanticSingleSelector.from_defaults(), query_engine_tools=[ summary_tool, vector_tool, ], )

In [ ]:

response = query_engine.query("What is the summary of the document?")

response = query_engine.query("What is the summary of the document?")

HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"
Selecting query engine 0: The choice is specifically related to summarization questions about Paul Graham's essay on What I Worked On..
HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"
HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"
HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"

In [ ]:

display(HTML(f'<p style="font-size:20px">{response.response}</p>'))

display(HTML(f'

{response.response}

'))

The document chronicles Paul Graham's journey through various endeavors, including his experiences with writing, programming, and founding software companies like Viaweb and Y Combinator. It discusses his exploration of painting, personal challenges such as his mother's illness, and his decision to step back from Y Combinator to focus on painting before returning to Lisp programming with the development of a new dialect called Bel. The narrative also covers Graham's reflections on his work choices, the transition of Y Combinator's leadership to Sam Altman, and his contemplation on future projects and the impact of customs in evolving fields.

LLMSingleSelector¶

利用 OpenAI（或其他大型语言模型）在内部解析生成的 JSON 数据，并确定用于路由的子索引。

In [ ]:

# Create Router Query Engine
query_engine = RouterQueryEngine(
    selector=LLMSingleSelector.from_defaults(),
    query_engine_tools=[
        summary_tool,
        vector_tool,
    ],
)

# Create Router Query Engine query_engine = RouterQueryEngine( selector=LLMSingleSelector.from_defaults(), query_engine_tools=[ summary_tool, vector_tool, ], )

In [ ]:

response = query_engine.query("What is the summary of the document?")

response = query_engine.query("What is the summary of the document?")

HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"
Selecting query engine 0: This choice indicates that the summary is related to summarization questions specifically about Paul Graham's essay on What I Worked On..
HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"
HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"
HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"

In [ ]:

display(HTML(f'<p style="font-size:20px">{response.response}</p>'))

display(HTML(f'

{response.response}

'))

The document chronicles Paul Graham's journey through various projects and endeavors, from his early experiences with writing and programming to his involvement in building software companies like Viaweb and Y Combinator. It details his exploration of different projects, challenges faced, decisions made, and eventual transition to focusing on painting and writing essays. The narrative also discusses his experimentation with the Lisp programming language and the development of a new Lisp dialect called Bel. The document concludes with Graham reflecting on his past projects and contemplating his future endeavors, emphasizing the importance of pursuing projects aligned with personal goals and interests.

In [ ]:

response = query_engine.query("What did Paul Graham do after RICS?")

response = query_engine.query("What did Paul Graham do after RICS?")

HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"
Selecting query engine 1: This choice is more relevant as it focuses on retrieving specific context from Paul Graham's essay on What I Worked On, which would likely provide information on what he did after RICS..
HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK"
HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"

In [ ]:

display(HTML(f'<p style="font-size:20px">{response.response}</p>'))

display(HTML(f'

{response.response}

'))

Paul Graham started painting after RICS.

PydanticMultiSelector¶

若预期查询会指向多个索引，建议使用多路选择器（multi-selector）。该选择器会将查询分发至多个子索引，随后通过摘要索引聚合各子索引的响应，最终返回综合答案。

让我们创建一个简单的关键词表索引及配套工具。¶

In [ ]:

from llama_index.core import SimpleKeywordTableIndex

keyword_index = SimpleKeywordTableIndex(nodes)

keyword_query_engine = keyword_index.as_query_engine()

keyword_tool = QueryEngineTool.from_defaults(
    query_engine=keyword_query_engine,
    description="Useful for retrieving specific context using keywords from Paul Graham essay on What I Worked On.",
)

from llama_index.core import SimpleKeywordTableIndex keyword_index = SimpleKeywordTableIndex(nodes) keyword_query_engine = keyword_index.as_query_engine() keyword_tool = QueryEngineTool.from_defaults( query_engine=keyword_query_engine, description="Useful for retrieving specific context using keywords from Paul Graham essay on What I Worked On.", )

构建路由查询引擎¶

In [ ]:

query_engine = RouterQueryEngine(
    selector=PydanticMultiSelector.from_defaults(),
    query_engine_tools=[vector_tool, keyword_tool, summary_tool],
)

query_engine = RouterQueryEngine( selector=PydanticMultiSelector.from_defaults(), query_engine_tools=[vector_tool, keyword_tool, summary_tool], )

In [ ]:

# This query could use either a keyword or vector query engine, so it will combine responses from both
response = query_engine.query(
    "What were noteable events and people from the authors time at Interleaf and YC?"
)

# This query could use either a keyword or vector query engine, so it will combine responses from both response = query_engine.query( "What were noteable events and people from the authors time at Interleaf and YC?" )

HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"
Selecting query engine 0: Retrieving specific context from Paul Graham essay on What I Worked On can provide detailed information about noteable events and people from the author's time at Interleaf and YC..
HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK"
HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"
Selecting query engine 1: Retrieving specific context using keywords from Paul Graham essay on What I Worked On can help identify key events and people related to the author's time at Interleaf and YC..
> Starting query: What were noteable events and people from the authors time at Interleaf and YC?
query keywords: ['noteable', 'authors', 'time', 'interleaf', 'yc', 'events', 'people']
> Extracted keywords: ['time', 'interleaf', 'yc', 'people']
HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"
Combining responses from multiple query engines.
HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"

In [ ]:

display(HTML(f'<p style="font-size:20px">{response.response}</p>'))

display(HTML(f'

{response.response}

'))

Notable events from the author's time at Interleaf include working on software development, observing inefficiencies in managing versions and ports, and learning about the dynamics of technology companies. Notable people mentioned from this time include Robert and Trevor, with whom the author worked on developing software components like the editor, shopping cart, and manager. During the author's time at Y Combinator (YC), notable events include working on various projects such as Hacker News, transitioning leadership to Sam Altman, and shifting focus towards painting after leaving YC. Notable people mentioned from this time include Julian, who provided seed funding for Viaweb, and Robert Morris, who advised the author about not letting YC be the last significant endeavor.

子问题查询引擎¶

本节将演示如何通过子问题查询引擎解决跨多数据源回答复杂查询的难题。

该引擎的工作原理是：首先将复杂查询拆解为针对各相关数据源的子问题，随后收集所有中间响应并综合生成最终答案。

下载数据¶

In [ ]:

!mkdir -p 'data/10k/'
!wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/docs/examples/data/10k/uber_2021.pdf' -O 'data/10k/uber_2021.pdf'
!wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/docs/examples/data/10k/lyft_2021.pdf' -O 'data/10k/lyft_2021.pdf'

!mkdir -p 'data/10k/' !wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/docs/examples/data/10k/uber_2021.pdf' -O 'data/10k/uber_2021.pdf' !wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/docs/examples/data/10k/lyft_2021.pdf' -O 'data/10k/lyft_2021.pdf'

--2024-05-16 05:36:06--  https://raw.githubusercontent.com/run-llama/llama_index/main/docs/docs/examples/data/10k/uber_2021.pdf
Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.108.133, 185.199.109.133, 185.199.110.133, ...
Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.108.133|:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: 1880483 (1.8M) [application/octet-stream]
Saving to: ‘data/10k/uber_2021.pdf’


data/10k/uber_2021.   0%[                    ]       0  --.-KB/s               
data/10k/uber_2021. 100%[===================>]   1.79M  --.-KB/s    in 0.01s   

2024-05-16 05:36:06 (184 MB/s) - ‘data/10k/uber_2021.pdf’ saved [1880483/1880483]

--2024-05-16 05:36:06--  https://raw.githubusercontent.com/run-llama/llama_index/main/docs/docs/examples/data/10k/lyft_2021.pdf
Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.110.133, 185.199.111.133, 185.199.109.133, ...
Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.110.133|:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: 1440303 (1.4M) [application/octet-stream]
Saving to: ‘data/10k/lyft_2021.pdf’

data/10k/lyft_2021. 100%[===================>]   1.37M  --.-KB/s    in 0.01s   

2024-05-16 05:36:06 (120 MB/s) - ‘data/10k/lyft_2021.pdf’ saved [1440303/1440303]

加载数据¶

In [ ]:

lyft_docs = SimpleDirectoryReader(
    input_files=["./data/10k/lyft_2021.pdf"]
).load_data()
uber_docs = SimpleDirectoryReader(
    input_files=["./data/10k/uber_2021.pdf"]
).load_data()

lyft_docs = SimpleDirectoryReader( input_files=["./data/10k/lyft_2021.pdf"] ).load_data() uber_docs = SimpleDirectoryReader( input_files=["./data/10k/uber_2021.pdf"] ).load_data()

In [ ]:

print(f"Loaded lyft 10-K with {len(lyft_docs)} pages")
print(f"Loaded Uber 10-K with {len(uber_docs)} pages")

print(f"Loaded lyft 10-K with {len(lyft_docs)} pages") print(f"Loaded Uber 10-K with {len(uber_docs)} pages")

Loaded lyft 10-K with 238 pages
Loaded Uber 10-K with 307 pages

创建索引¶

In [ ]:

lyft_index = VectorStoreIndex.from_documents(lyft_docs)
uber_index = VectorStoreIndex.from_documents(uber_docs)

lyft_index = VectorStoreIndex.from_documents(lyft_docs) uber_index = VectorStoreIndex.from_documents(uber_docs)

HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK"
HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK"
HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK"
HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK"
HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK"
HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK"
HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK"
HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK"
HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK"

定义查询引擎¶

In [ ]:

lyft_engine = lyft_index.as_query_engine(similarity_top_k=3)

lyft_engine = lyft_index.as_query_engine(similarity_top_k=3)

In [ ]:

uber_engine = uber_index.as_query_engine(similarity_top_k=3)

uber_engine = uber_index.as_query_engine(similarity_top_k=3)

In [ ]:

response = await lyft_engine.aquery(
    "What is the revenue of Lyft in 2021? Answer in millions with page reference"
)

response = await lyft_engine.aquery( "What is the revenue of Lyft in 2021? Answer in millions with page reference" )

HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK"
HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"

In [ ]:

display(HTML(f'<p style="font-size:20px">{response.response}</p>'))

display(HTML(f'

{response.response}

'))

The revenue of Lyft in 2021 was $3.208 billion. (Page reference: 79)

In [ ]:

response = await uber_engine.aquery(
    "What is the revenue of Uber in 2021? Answer in millions, with page reference"
)

response = await uber_engine.aquery( "What is the revenue of Uber in 2021? Answer in millions, with page reference" )

HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK"
HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"

In [ ]:

display(HTML(f'<p style="font-size:20px">{response.response}</p>'))

display(HTML(f'

{response.response}

'))

The revenue of Uber in 2021 was $17,455 million. (Reference: page 77)

定义查询引擎工具¶

In [ ]:

query_engine_tools = [
    QueryEngineTool(
        query_engine=lyft_engine,
        metadata=ToolMetadata(
            name="lyft_10k",
            description="Provides information about Lyft financials for year 2021",
        ),
    ),
    QueryEngineTool(
        query_engine=uber_engine,
        metadata=ToolMetadata(
            name="uber_10k",
            description="Provides information about Uber financials for year 2021",
        ),
    ),
]

query_engine_tools = [ QueryEngineTool( query_engine=lyft_engine, metadata=ToolMetadata( name="lyft_10k", description="Provides information about Lyft financials for year 2021", ), ), QueryEngineTool( query_engine=uber_engine, metadata=ToolMetadata( name="uber_10k", description="Provides information about Uber financials for year 2021", ), ), ]

子问题查询引擎¶

In [ ]:

from llama_index.core.query_engine.sub_question_query_engine import (
    SubQuestionQueryEngine,
)

sub_question_query_engine = SubQuestionQueryEngine.from_defaults(
    query_engine_tools=query_engine_tools
)

from llama_index.core.query_engine.sub_question_query_engine import ( SubQuestionQueryEngine, ) sub_question_query_engine = SubQuestionQueryEngine.from_defaults( query_engine_tools=query_engine_tools )

查询¶

In [ ]:

response = await sub_question_query_engine.aquery(
    "Compare revenue growth of Uber and Lyft from 2020 to 2021"
)

response = await sub_question_query_engine.aquery( "Compare revenue growth of Uber and Lyft from 2020 to 2021" )

HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"
Generated 4 sub questions.
[uber_10k] Q: What was the revenue of Uber in 2020?
[uber_10k] Q: What was the revenue of Uber in 2021?
[lyft_10k] Q: What was the revenue of Lyft in 2020?
[lyft_10k] Q: What was the revenue of Lyft in 2021?
HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK"
HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK"
HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK"
HTTP Request: POST https://api.openai.com/v1/embeddings "HTTP/1.1 200 OK"
HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"
[lyft_10k] A: $3,208,323
HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"
[lyft_10k] A: $2,364,681
HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"
[uber_10k] A: $11,139 million
HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"
[uber_10k] A: $17,455
HTTP Request: POST https://api.openai.com/v1/chat/completions "HTTP/1.1 200 OK"

In [ ]:

display(HTML(f'<p style="font-size:20px">{response.response}</p>'))

display(HTML(f'

{response.response}

'))

Lyft's revenue grew by approximately 35.4% from 2020 to 2021, while Uber's revenue increased by around 56.8% during the same period.